Re: [PATCH 3/3] Page Fault Scalability V20: Avoid lock for anonymous write fault

From: Christoph Lameter <clameter_at_engr.sgi.com>
Date: 2005-04-30 09:06:59
On Fri, 29 Apr 2005, Christoph Hellwig wrote:

> On Fri, Apr 29, 2005 at 12:59:17PM -0700, Christoph Lameter wrote:
> > Do not use the page_table_lock in do_anonymous_page. This will significantly
> > increase the parallelism in the page fault handler for SMP systems. The patch
> > also modifies the definitions of _mm_counter functions so that rss and anon_rss
> > become atomic (and will use atomic64_t if available).
>
> I thought we said all architectures should provide an atomic64_t (and
> given that it's not actually 64bit on 32bit architecture we should
> probably rename it to atomic_long_t)

Yes the way atomic types are provided may need a revision.
First of all we need atomic types that are size bound

	atomic8_t
	atomic16_t
	atomic32_t

and (if available)

	atomic64_t

and then some aliases

	atomic_t -> atomic type for int
	atomic_long_t -> atomic type for long

If these types are available then this patch could be cleaned up to
just use atomic_long_t.
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Received on Fri Apr 29 19:07:30 2005

This archive was generated by hypermail 2.1.8 : 2005-08-02 09:20:37 EST